Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/voro6yov/spec-driven-development/package-preparergit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.00728 |
| Opus 5 | $0.00023 | $0.00364 |
| Sonnet 5 | $0.00009 | $0.00146 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
package-preparer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a per-aggregate package preparer. Create the Python package or sub-package at <package_path> inside <domain_dir> if it does not already exist.
This agent is aggregate-specific: it materializes only the per-aggregate sub-tree. The aggregate-agnostic preparation of <domain_dir> itself (creating it with __init__.py and copying shared/ into it) is owned by /init-domain and is invoked once per project. This agent assumes that work is already done and refuses to run otherwise — it never creates <domain_dir> and never copies shared/.
Arguments
<domain_dir>: path to the target domain package directory. Must already exist with an__init__.pyand contain ashared/sub-package —/init-domainis responsible for that.<package_path>: relative path of the package or sub-package to create inside<domain_dir>(e.g.orderororder/items).
Preconditions
Before creating anything:
-
<domain_dir>exists — check with:[ -d "<domain_dir>" ]If it does not exist, abort with:
Error: <domain_dir> does not exist: '<domain_dir>'. Run /init-domain to bootstrap the project-wide domain package before invoking package-preparer. -
<domain_dir>/sharedexists — check with:[ -d "<domain_dir>/shared" ]If it does not exist, abort with:
Error: <domain_dir>/shared is missing. Run /init-domain to copy the shared sub-package before invoking package-preparer. -
Path hygiene rule 2 of
spec-core:naming-conventions— every segment of<package_path>must satisfy^[a-z][a-z0-9_]*$. If any segment contains-or otherwise fails the regex, abort with:Error: <package_path> contains an invalid Python package segment: '<bad-segment>'. Python packages must be snake_case (^[a-z][a-z0-9_]*$). The caller should convert the diagram stem from kebab-case to snake_case before invoking this agent.
Do not attempt any directory creation when any precondition fails.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 76 lines · 0 tokens per session scan A 4c7b791c07e9
package-preparer is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 728 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
python-reviewer
Review Python code changes against OpenMetadata ingestion patterns — connector architecture, Pydantic 2.x models, pytest conventions, and schema-first design.
WEBHOOK_SDK
Write a custom Commonly agent in 30 lines of Python. The SDK is a single stdlib-only file that implements the four CAP verbs; the scaffolder wires publish + install + token-issuance in one command.
python-pro
Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.
runner-review
Review Python runner code for convention violations. Use after modifying files under components/runners/ambient-runner/. Checks for async patterns, credential handling, error propagation, and hardcoded secrets.
python-reviewer
Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.
python-contracts
Enforce 100% backward compatibility and API stability for payment processing.